© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16902
    Prev
    Next
    INDEX
    Explanations

    .com/ or writing applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auer
    -0.09
    æľªå¿ħ
    -0.08
    ä¸ĭè½½æĬ¥åijĬ
    -0.08
    å¾Ĺè¿ĩ
    -0.07
    oney
    -0.07
    æľ¬æĸĩ为åįļ主
    -0.07
    èĥ½ä¿ĥè¿Ľ
    -0.07
    ãĥªãĥĥãĥĹ
    -0.07
    è´«
    -0.07
    ideos
    -0.07
    POSITIVE LOGITS
     efficiently
    0.08
    ä¿ĿæĮģäºĨ
    0.07
     straightforward
    0.07
     ensures
    0.07
    åģļåĪ°äºĨ
    0.07
    ç¡®ä¿ĿäºĨ
    0.07
     avoids
    0.07
     computational
    0.06
    éģ¿åħįäºĨ
    0.06
    _CAST
    0.06
    Activations Density 0.001%

    No Known Activations